{"created":"2025-01-19T01:29:32.017772+00:00","updated":"2025-01-19T11:19:17.584913+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00230022","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"230022","title":["深層予測学習の予測誤差に基づく時系列データの自動分節化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"765a2123-7479-4ff0-ae4d-d7eef606bc9b"},"_deposit":{"id":"230022","pid":{"type":"depid","value":"230022","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"深層予測学習の予測誤差に基づく時系列データの自動分節化","author_link":["618846","618845","618848","618847"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"深層予測学習の予測誤差に基づく時系列データの自動分節化"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2023-02-16","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"早稲田大　/　産総研"},{"subitem_text_value":"産総研　/　早稲田大"},{"subitem_text_value":"早稲田大　/　産総研"},{"subitem_text_value":"早稲田大　/　産総研"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/230022/files/IPSJ-Z85-6S-03.pdf","label":"IPSJ-Z85-6S-03.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-6S-03.pdf","filesize":[{"value":"557.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"4084807f-490c-47e9-9c59-a37f691b5e59","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"原田, 紗圭"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中條, 亨一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"加瀬, 敬唯"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"尾形, 哲也"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"ロボットの動作学習において，経験に基づく知識情報をデータに付与することでパフォーマンスの向上が期待できる．先行研究では動作タスクの分節化はロボット動作学習の汎化性上昇やタスク認識に応用できることを示した．一方で，人の主観に基づくタスクの分節化は作業者によって分節位置のズレが生じる上，大量のデータを分節するためには作業コストが非常に高くなる．本研究では深層学習を用いた予測学習において，分節区間ごとの予測誤差の大小を比較して分節位置を更新する自動分節化の手法を提案した．ロボットの運動時系列を想定したリサージュ曲線を用いた時系列データにおいて，予測誤差に基づく自動分節化は可能であることが確認された．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"454","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"453","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":230022,"links":{}}